© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16766
    Prev
    Next
    INDEX
    Explanations

    light, star, altitude, soar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    æ°ı
    -0.05
    ç»Ĩèĥŀ
    -0.05
     tote
    -0.05
     оÑģÑĤоÑĢо
    -0.04
    家
    -0.04
    åŁºæķ°
    -0.04
    对象
    -0.04
     Jacqu
    -0.04
    æĿĢ
    -0.04
    åľ°
    -0.04
    POSITIVE LOGITS
    escort
    0.07
    kaç
    0.07
    æ´ŀå¯ŁåĬĽ
    0.07
    -guid
    0.07
    eguard
    0.07
    arbet
    0.06
     inal
    0.06
    revet
    0.06
     minded
    0.06
    sbin
    0.06
    Activations Density 0.003%

    No Known Activations